no code implementations • 11 Aug 2020 • Liqiang Song, Ye Bi, Mengqiu Yao, Zhen-Yu Wu, Jianming Wang, Jing Xiao
In this paper, we propose a unified framework named Dynamic RElation Aware Model (DREAM) for social recommendation, which tries to model both users dynamic interests and their friends temporal influences.
no code implementations • 10 Aug 2020 • Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
In sharp contrast to the state-of-the-art (SOTA) methods that focus on learning pixel-wise saliency in "single image" using perceptual clues mainly, our method has investigated the "object-level semantic ranks between multiple images", of which the methodology is more consistent with the real human attention mechanism.
1 code implementation • 7 Aug 2020 • Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
Finally, all these complementary multi-model deep features will be selectively fused to make high-performance salient object detections.
no code implementations • 7 Aug 2020 • Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy networks over large-scale training sets.
no code implementations • 6 Aug 2020 • Bo Huang, Ye Bi, Zhen-Yu Wu, Jianming Wang, Jing Xiao
The problem of session-based recommendation aims to predict user next actions based on session histories.
1 code implementation • 30 Jul 2020 • Ye Bi, Liqiang Song, Mengqiu Yao, Zhen-Yu Wu, Jianming Wang, Jing Xiao
Specifically, we first try to learn more effective user and item latent features in both source and target domains.
no code implementations • 27 Jul 2020 • Ye Bi, Liqiang Song, Mengqiu Yao, Zhen-Yu Wu, Jianming Wang, Jing Xiao
In this paper, we propose a Deep Cross Domain Insurance Recommendation System (DCDIR) for cold start users.
no code implementations • 17 Jun 2020 • Jianrong Wang, Ge Zhang, Zhen-Yu Wu, XueWei Li, Li Liu
Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects.
no code implementations • 31 Oct 2019 • Li-Phen Yen, Zhen-Yu Wu, Kuan-Yu Chen
Recent developments in deep learning have led to a significant innovation in various classic and practical subjects, including speech recognition, computer vision, question answering, information retrieval and so on.
2 code implementations • ICCV 2019 • Zhen-Yu Wu, Karthik Suresh, Priya Narayanan, Hongyu Xu, Heesung Kwon, Zhangyang Wang
Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful.
5 code implementations • 12 Jun 2019 • Zhen-Yu Wu, Haotao Wang, Zhaowen Wang, Hailin Jin, Zhangyang Wang
We first discuss an innovative heuristic of cross-dataset training and evaluation, enabling the use of multiple single-task datasets (one with target task labels and the other with privacy labels) in our problem.
1 code implementation • 30 May 2019 • Pritish Uplavikar, Zhen-Yu Wu, Zhangyang Wang
We train our model on a dataset consisting images of 10 Jerlov water types.
no code implementations • 19 Nov 2018 • Wenfang Lin, Zhen-Yu Wu, Yang Ji
Data-driven fault diagnostics and prognostics suffers from class-imbalance problem in industrial systems and it raises challenges to common machine learning algorithms as it becomes difficult to learn the features of the minority class samples.
3 code implementations • ECCV 2018 • Zhen-Yu Wu, Zhangyang Wang, Zhaowen Wang, Hailin Jin
This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework.
1 code implementation • ICML 2018 • Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
1 code implementation • 25 Jun 2018 • Peng Gao, Xusheng Xiao, Ding Li, Zhichun Li, Kangkook Jee, Zhen-Yu Wu, Chung Hwan Kim, Sanjeev R. Kulkarni, Prateek Mittal
To facilitate the task of expressing anomalies based on expert knowledge, our system provides a domain-specific query language, SAQL, which allows analysts to express models for (1) rule-based anomalies, (2) time-series anomalies, (3) invariant-based anomalies, and (4) outlier-based anomalies.
Cryptography and Security Databases
1 code implementation • 24 Jun 2018 • Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
no code implementations • 18 Nov 2015 • Bo Zong, Xusheng Xiao, Zhichun Li, Zhen-Yu Wu, Zhiyun Qian, Xifeng Yan, Ambuj K. Singh, Guofei Jiang
In this work, we investigate how to query temporal graphs and treat query formulation as a discriminative temporal graph pattern mining problem.